Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1068 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.3082. Min Range: -3.3082

Max Act: 3.3082. Min Act: -0.0000

Data Index: 1267848 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.8127. Min Act: -0.0000

Data Index: 1717748 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.9408. Min Act: -0.0000

Data Index: 690728 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.8577. Min Act: -0.0000

Data Index: 1610454 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.7191. Min Act: -0.0000

Data Index: 218453 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.6978. Min Act: -0.0000

Data Index: 1834052 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.6161. Min Act: -0.0000

Data Index: 13243 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.5755. Min Act: -0.0000

Data Index: 1949912 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.5610. Min Act: -0.0000

Data Index: 1475199 (The Pile)

Max Activating Token Index: 334

Text #9

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.5368. Min Act: -0.0000

Data Index: 425431 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.4332. Min Act: -0.0000

Data Index: 1472462 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.5384. Min Act: -0.0000

Data Index: 1302994 (The Pile)

Max Activating Token Index: 822

Text #12

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.4344. Min Act: -0.0000

Data Index: 160877 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.3725. Min Act: -0.0000

Data Index: 1391914 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.4718. Min Act: -0.0000

Data Index: 118081 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.3318. Min Act: -0.0000

Data Index: 1868700 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.5746. Min Act: -0.0000

Data Index: 1678286 (The Pile)

Max Activating Token Index: 183

Text #17

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.4471. Min Act: -0.0000

Data Index: 409568 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.4299. Min Act: -0.0000

Data Index: 1521586 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 3.3082. Min Range: -3.3082

Max Act: 2.5731. Min Act: -0.0000

Data Index: 1179244 (The Pile)

Max Activating Token Index: 913